Academic Betadiversity and Future of Biology Research
Ben Weinstein
Thursday, April 23, 2015
#Scopus Database Query By Journal Article
library(XML)
library(proto)
library(magrittr)
library(broom)
library(plyr)
library(dplyr)
library(ggplot2)
library(reshape2)
library(httr)
library(stringr)
library(chron)
library(vegan)
library(knitr)
library(bipartite)
library(sna)
library(igraph)
library(knitr)
library(gridExtra)
library(GGally)
library(stringr)
library(networkD3)#source functions
source("Funtions.R")
#set knitr options
opts_chunk$set(echo=T,cache=F,fig.align='center',fig.height=15,fig.width=14,warning=F,message=F)Read in data. Processed from ByJournal.R
#journal class
journaldf<-read.csv("C:/Users/Ben/Dropbox/FacultyNetwork/JournalID.csv",row.names=1)
tocompare<-read.table("C:/Users/Ben/Dropbox/FacultyNetwork/ParsedDataID.csv",row.names=NULL,header=T,sep=",",fill=T)
#what does it look like:
tail(tocompare)## Journal DOI Order Author
## 4763443 Zoologica Scripta SCOPUS_ID:84927938292 3 7005747774
## 4763444 Zoologica Scripta SCOPUS_ID:84927938292 4 8692718700
## 4763445 Zoologica Scripta SCOPUS_ID:84927938292 2 56596457600
## 4763446 Zoologica Scripta SCOPUS_ID:84927938292 1 54890209300
## 4763447 Zoologica Scripta SCOPUS_ID:84927938292 6 6701851552
## 4763448 Zoologica Scripta SCOPUS_ID:84927938292 5 6506098243
## Affiliation
## 4763443 Universita degli Studi del Molise
## 4763444 Universita di Pisa
## 4763445 Museo Civico di Storia Naturale di Trieste
## 4763446 Dipartimento di Biologia Univerisità degli Studi di Napoli Federico II
## 4763447 Universita degli Studi di Napoli Federico II
## 4763448 University of Belgrade
## Citations Year Class h5.index h5.median
## 4763443 0 2015 Zoology 23 27
## 4763444 0 2015 Zoology 23 27
## 4763445 0 2015 Zoology 23 27
## 4763446 0 2015 Zoology 23 27
## 4763447 0 2015 Zoology 23 27
## 4763448 0 2015 Zoology 23 27dim(tocompare)## [1] 4763448 10#remove biogeneral i think for now
tocompare<-tocompare[!tocompare$Class %in% "Biogeneral",]Basic data cleaning. We only want records from active authors. Atleast 5 publications in the entire record.
#filter authors
#distribution of publication
keep<-names(which(table(tocompare$Author)>3))
tocompare<-droplevels(tocompare[tocompare$Author %in% keep,])
#remove duplicates.
tocompare<-tocompare[!duplicated(tocompare),]
#in case the column names in there
tocompare<-droplevels(tocompare[!tocompare$Journal %in% "DOI",])
dim(tocompare)## [1] 2715847 10j_class<-read.csv("Class.csv",row.names=1)
#in case there are malformed classes
tocompare<-droplevels(tocompare[tocompare$Class %in% j_class$Class,])
#take out malformed lines
tocompare<-tocompare[which(!str_detect(tocompare$Journal, "SCOPUS")),]
#take year 2015
tocompare<-tocompare[!tocompare$Year %in% 2015,]
tocompare<-droplevels(tocompare[which(!str_detect(tocompare$h5.index, "SCOPUS")),])
dim(tocompare)## [1] 2659518 10Basic descriptive stats on results
#How many journals
paste("Number of Journals:",length(unique(tocompare$Journal)))## [1] "Number of Journals: 578"#How many authors
paste("Number of Authors:",length(unique(tocompare$Author)))## [1] "Number of Authors: 327175"#How many papers
paste("Number of Papers:",length(unique(tocompare$DOI)))## [1] "Number of Papers: 1325937"ta<-sort(table(tocompare$Journal))
print("Most published journals")## [1] "Most published journals"tail(ta)##
## Journal Of Virology Oncogene
## 36572 40980
## Atmospheric Environment Nucleic Acids Research
## 45494 54840
## Molecular And Cellular Biology Journal Of Biological Chemistry
## 66726 77452How many papers from each discipline over time?
class_year<-group_by(tocompare,Class,Year) %>% summarize(Papers=length(unique(DOI)))
ggplot(class_year,aes(x=as.factor(Year),y=Papers,col=Class,group=Class)) + geom_line() + theme_bw() + facet_wrap(~Class,scale="free_y",ncol=4) + labs(x="Year")
ggsave("Figures/Papers_Year.svg",dpi=300)Create matrix of authors in each class - analagous to the site by species matrix used in ecology
siteXspp<-as.data.frame.array(table(tocompare$Author,tocompare$Class))
dim(siteXspp)## [1] 327175 38Dissimalarity among classes
Use the abundance of papers by each author to calculate niche overlap (dist=1-Horn’s) between classes.
Low overlap=0 High overlap=1
#Compare disciplines
topics<-1-as.matrix(vegdist(t(siteXspp),"horn"))Visualize interactions.
- Stronger interactions are more red.
- Weaker interactions are blue.
- Stronger connections are thicker
- Weaker connections are thinner
- More central members (greater number of partners) are in larger text
- Less central members (fewer number of partners) are in smaller text
g<-graph.adjacency(topics,"undirected",weighted=TRUE)
g<-simplify(g)
# set labels and degrees of vertices
V(g)$label <- V(g)$name
V(g)$degree <- degree(g)
V(g)$label.color <- rgb(0, 0, .2, .8)
V(g)$frame.color <- NA
egam=E(g)$weight/max(E(g)$weight)
E(g)$color<-rgb(0,1,0,alpha=E(g)$weight/max(E(g)$weight),maxColorValue=1)
ramp <- colorRamp(c("blue","red"),alpha=T)
E(g)$color = apply(ramp(E(g)$weight), 1, function(x) rgb(x[1]/255,x[2]/255,x[3]/255,alpha=T) )
#If you need to delete
g.copy <- delete.edges(g, which(E(g)$weight<.05))
#width
width<-(E(g.copy)$weight/max(E(g.copy)$weight))*8
#label sizes
V(g.copy)$degree <- degree(g.copy)
V(g.copy)$label.cex <- V(g.copy)$degree / max(V(g.copy)$degree)*.5+.5
#get vertex size
size<-group_by(tocompare,Class) %>% summarize(Papers=length(unique(DOI)))
size<-round(as.numeric(table(tocompare$Class))/max(table(tocompare$Class))*5)+2
#scale
plot.igraph(g.copy,vertex.size=size,edge.width=width)
#try a couple different layouts
# plot the graph in layout1
layout1 <- layout.fruchterman.reingold(g.copy,niter=10000,area=vcount(g.copy)^2.3)
plot(g.copy,edge.width=width,vertex.size=size,layout=layout1,vertex.color="grey40")
# plot the graph in layout1
layout2 <- layout.reingold.tilford(g.copy,circular=T)
plot(g.copy,edge.width=width,vertex.size=size,layout=layout2,vertex.color="grey70")
# plot the graph in layout3
layout3 <- layout.kamada.kawai(g.copy,niter=5000)
plot(g.copy,edge.width=width,vertex.size=size,layout=layout3,vertex.color="grey40")
#save full network
svg(filename = "Figures/Overall_NetworkIgraph.svg",width=10,height=10)
plot(g.copy,edge.width=width,vertex.size=size,layout=layout1,vertex.color="grey40")
dev.off()## pdf
## 2jpeg(filename = "Figures/Overall_NetworkIgraph.jpeg",res=300,height=12,width=10,units="in")
plot(g.copy,edge.width=width,vertex.size=size,layout=layout1,vertex.color="grey40")
dev.off()## pdf
## 2View as a dendrogram
wt <- walktrap.community(g, modularity=TRUE)
dend <- as.dendrogram(wt, use.modularity=TRUE)
plot(as.hclust(dend))
Calculate network statistics
We are interested in the centrality, modularity and compartamentalization of the biological sciences
- Betweenness - number of shortest path that includes node. This tends to find gatekeeps among components.
- Degree - number of connections for each node
- Closeness - relative distance to all actors
- Coreness - The centrality of network position.
- Eigenvector centrality: A node is important if it is connected to many important nodes. A node with a small number of influential contacts will be better than a larger number of mediocre contacts.
between_class<-betweenness(g.copy)
degree_class<-degree(g.copy)
closeness_class<-closeness(g.copy)
eigenV<-evcent(g.copy)$vector
vdat<-data.frame(Class=names(between_class),Between=between_class,Degree=degree_class,Closeness=closeness_class,Eigen=eigenV)Correlation among importance measures.
ggpairs(vdat[,-1])
#reoroder levels
vdat$Class<-factor(vdat$Class,levels=vdat[order(vdat$Between,vdat$Degree),"Class"])Top actors for each statistic
mdat<-melt(vdat)
colnames(mdat)<-c("Class","Metric","Score")
#order and plot
dt<-group_by(mdat,Metric) %>% mutate(Svalue=as.numeric(scale(Score))) %>% group_by(Metric,Class) %>% arrange(Score)
ggplot(dt,aes(y=Class,x=Svalue)) + geom_bar_horz(stat="identity",position="identity") + facet_grid(.~Metric) + labs(x="Z-score")
ggsave("Figures/OveralMetrics.jpg",dpi=300,height=10,width=12)
ggsave("Figures/OveralMetrics.svg",dpi=300)Average connectedness and degree and link strength
group_by(mdat,Metric) %>% summarize(mean=mean(Score))## Source: local data frame [4 x 2]
##
## Metric mean
## 1 Between 42.34211
## 2 Degree 4.68421
## 3 Closeness 0.01971
## 4 Eigen 0.17676overall.density<-graph.density(g.copy)
mean(E(g.copy)$weight)## [1] 0.1403Network stats over time
#split into a time frame 5 years?
m<-seq(1995,2014,2)
tocompare$Time<-cut(as.numeric(as.character(tocompare$Year)),breaks=m,labels=m[1:length(m)-1])
yearcompare<-split(tocompare,tocompare$Time)
#all over
#caculate degree distribution
dd<-melt(sapply(yearcompare,CalcDD))
ggplot(dd,aes(x=Var1,y=value,col=as.factor(L1))) + geom_line(size=.5) + geom_point(size=4,aes(group=as.factor(L1))) + theme_bw() + xlab("Node Degree") + ggtitle("Degree Distribution") + labs(col="Year") 
yearstats<-lapply(yearcompare,calcN)
head(yearstats)## $`1995`
## Class
## Agronomy Crop Science Agronomy Crop Science
## Animal Behavior Animal Behavior
## Animal Husbandry Animal Husbandry
## Atmospheric Sciences Atmospheric Sciences
## Biochemistry Biochemistry
## Biodiversity & Conservation Biology Biodiversity & Conservation Biology
## Bioinformatics Bioinformatics
## Biophysics Biophysics
## Biotechnology Biotechnology
## Birds Birds
## Botany Botany
## Cell Biology Cell Biology
## Developmental Biology & Embryology Developmental Biology & Embryology
## Ecology Ecology
## Environmental & Geological Engineering Environmental & Geological Engineering
## Environmental Sciences Environmental Sciences
## Evolutionary Biology Evolutionary Biology
## Food Science & Technology Food Science & Technology
## Forests & Forestry Forests & Forestry
## Geochemistry & Mineralogy Geochemistry & Mineralogy
## Geology Geology
## Hydrology Hydrology
## Insects & Arthropods Insects & Arthropods
## Marine Sciences Fisheries Marine Sciences Fisheries
## Microbiology Microbiology
## Molecular Biology Molecular Biology
## Mycology Mycology
## Oceanography Oceanography
## Paleontology Paleontology
## Pest Control & Pesticides Pest Control & Pesticides
## Plant Pathology Plant Pathology
## Proteomics & Peptides Proteomics & Peptides
## Soil Sciences Soil Sciences
## Sustainable Development Sustainable Development
## Sustainable Energy Sustainable Energy
## Virology Virology
## Wood Science & Technology Wood Science & Technology
## Zoology Zoology
## Between Degree Closeness Eigen
## Agronomy Crop Science 24 3 0.0021109 0.000e+00
## Animal Behavior 35 4 0.0021493 7.636e-04
## Animal Husbandry 27 2 0.0021458 7.274e-04
## Atmospheric Sciences 0 2 0.0021367 0.000e+00
## Biochemistry 1 2 0.0007515 7.035e-01
## Biodiversity & Conservation Biology 0 3 0.0021423 0.000e+00
## Bioinformatics 0 0 0.0007112 2.979e-04
## Biophysics 0 1 0.0007310 7.026e-04
## Biotechnology 49 3 0.0021461 1.383e-03
## Birds 0 3 0.0021493 3.369e-05
## Botany 46 2 0.0021187 6.297e-04
## Cell Biology 0 2 0.0007513 9.387e-01
## Developmental Biology & Embryology 0 0 0.0007112 2.979e-04
## Ecology 177 7 0.0021548 0.000e+00
## Environmental & Geological Engineering 0 1 0.0021445 3.073e-04
## Environmental Sciences 162 6 0.0021520 0.000e+00
## Evolutionary Biology 0 2 0.0021449 0.000e+00
## Food Science & Technology 25 2 0.0021450 1.078e-03
## Forests & Forestry 0 0 0.0007112 2.979e-04
## Geochemistry & Mineralogy 0 1 0.0021151 7.143e-05
## Geology 47 3 0.0021347 4.324e-04
## Hydrology 0 0 0.0007112 2.979e-04
## Insects & Arthropods 100 2 0.0021511 2.441e-04
## Marine Sciences Fisheries 118 3 0.0021532 0.000e+00
## Microbiology 22 2 0.0021442 9.731e-04
## Molecular Biology 0 2 0.0007513 1.000e+00
## Mycology 0 0 0.0007112 2.979e-04
## Oceanography 87 4 0.0021468 0.000e+00
## Paleontology 0 1 0.0021125 0.000e+00
## Pest Control & Pesticides 84 2 0.0021348 6.581e-05
## Plant Pathology 66 3 0.0021254 0.000e+00
## Proteomics & Peptides 0 1 0.0007310 7.026e-04
## Soil Sciences 0 1 0.0020801 0.000e+00
## Sustainable Development 0 1 0.0021461 4.057e-04
## Sustainable Energy 0 1 0.0021395 5.235e-04
## Virology 0 0 0.0007112 2.979e-04
## Wood Science & Technology 0 0 0.0007112 2.979e-04
## Zoology 23 4 0.0021480 8.343e-05
##
## $`1997`
## Class
## Agronomy Crop Science Agronomy Crop Science
## Animal Behavior Animal Behavior
## Animal Husbandry Animal Husbandry
## Atmospheric Sciences Atmospheric Sciences
## Biochemistry Biochemistry
## Biodiversity & Conservation Biology Biodiversity & Conservation Biology
## Bioinformatics Bioinformatics
## Biophysics Biophysics
## Biotechnology Biotechnology
## Birds Birds
## Botany Botany
## Cell Biology Cell Biology
## Developmental Biology & Embryology Developmental Biology & Embryology
## Ecology Ecology
## Environmental & Geological Engineering Environmental & Geological Engineering
## Environmental Sciences Environmental Sciences
## Evolutionary Biology Evolutionary Biology
## Food Science & Technology Food Science & Technology
## Forests & Forestry Forests & Forestry
## Geochemistry & Mineralogy Geochemistry & Mineralogy
## Geology Geology
## Hydrology Hydrology
## Insects & Arthropods Insects & Arthropods
## Marine Sciences Fisheries Marine Sciences Fisheries
## Microbiology Microbiology
## Molecular Biology Molecular Biology
## Mycology Mycology
## Oceanography Oceanography
## Paleontology Paleontology
## Pest Control & Pesticides Pest Control & Pesticides
## Plant Pathology Plant Pathology
## Proteomics & Peptides Proteomics & Peptides
## Soil Sciences Soil Sciences
## Sustainable Development Sustainable Development
## Sustainable Energy Sustainable Energy
## Virology Virology
## Wood Science & Technology Wood Science & Technology
## Zoology Zoology
## Between Degree Closeness Eigen
## Agronomy Crop Science 23 3 0.0019900 8.694e-04
## Animal Behavior 41 5 0.0019942 1.525e-04
## Animal Husbandry 27 2 0.0019904 5.283e-04
## Atmospheric Sciences 0 2 0.0019789 0.000e+00
## Biochemistry 0 2 0.0007515 7.310e-01
## Biodiversity & Conservation Biology 24 4 0.0019887 0.000e+00
## Bioinformatics 0 0 0.0007112 8.761e-05
## Biophysics 0 1 0.0007309 1.770e-04
## Biotechnology 23 2 0.0019896 2.975e-04
## Birds 32 3 0.0019942 0.000e+00
## Botany 101 3 0.0019957 1.581e-04
## Cell Biology 0 2 0.0007513 9.432e-01
## Developmental Biology & Embryology 0 0 0.0007112 8.761e-05
## Ecology 162 7 0.0019984 0.000e+00
## Environmental & Geological Engineering 0 1 0.0019887 3.196e-05
## Environmental Sciences 128 5 0.0019942 3.824e-04
## Evolutionary Biology 0 3 0.0019910 0.000e+00
## Food Science & Technology 23 2 0.0019885 5.556e-04
## Forests & Forestry 0 1 0.0019837 0.000e+00
## Geochemistry & Mineralogy 0 1 0.0019596 1.386e-04
## Geology 45 3 0.0019783 2.807e-04
## Hydrology 0 0 0.0007112 8.761e-05
## Insects & Arthropods 0 1 0.0019544 4.412e-04
## Marine Sciences Fisheries 103 3 0.0019966 0.000e+00
## Microbiology 18 2 0.0019873 4.969e-04
## Molecular Biology 0 2 0.0007512 1.000e+00
## Mycology 0 0 0.0007112 8.761e-05
## Oceanography 63 4 0.0019891 0.000e+00
## Paleontology 0 1 0.0019635 1.205e-04
## Pest Control & Pesticides 23 2 0.0019787 8.262e-04
## Plant Pathology 44 3 0.0019885 6.083e-04
## Proteomics & Peptides 0 1 0.0007309 1.770e-04
## Soil Sciences 0 1 0.0019630 2.063e-04
## Sustainable Development 0 0 0.0007112 8.761e-05
## Sustainable Energy 0 0 0.0007112 8.761e-05
## Virology 0 0 0.0007112 8.761e-05
## Wood Science & Technology 0 0 0.0007112 8.761e-05
## Zoology 10 4 0.0019923 0.000e+00
##
## $`1999`
## Class
## Agronomy Crop Science Agronomy Crop Science
## Animal Behavior Animal Behavior
## Animal Husbandry Animal Husbandry
## Atmospheric Sciences Atmospheric Sciences
## Biochemistry Biochemistry
## Biodiversity & Conservation Biology Biodiversity & Conservation Biology
## Bioinformatics Bioinformatics
## Biophysics Biophysics
## Biotechnology Biotechnology
## Birds Birds
## Botany Botany
## Cell Biology Cell Biology
## Developmental Biology & Embryology Developmental Biology & Embryology
## Ecology Ecology
## Environmental & Geological Engineering Environmental & Geological Engineering
## Environmental Sciences Environmental Sciences
## Evolutionary Biology Evolutionary Biology
## Food Science & Technology Food Science & Technology
## Forests & Forestry Forests & Forestry
## Geochemistry & Mineralogy Geochemistry & Mineralogy
## Geology Geology
## Hydrology Hydrology
## Insects & Arthropods Insects & Arthropods
## Marine Sciences Fisheries Marine Sciences Fisheries
## Microbiology Microbiology
## Molecular Biology Molecular Biology
## Mycology Mycology
## Oceanography Oceanography
## Paleontology Paleontology
## Pest Control & Pesticides Pest Control & Pesticides
## Plant Pathology Plant Pathology
## Proteomics & Peptides Proteomics & Peptides
## Soil Sciences Soil Sciences
## Sustainable Development Sustainable Development
## Sustainable Energy Sustainable Energy
## Virology Virology
## Wood Science & Technology Wood Science & Technology
## Zoology Zoology
## Between Degree Closeness Eigen
## Agronomy Crop Science 4 3 0.0008215 1.387e-03
## Animal Behavior 33 5 0.0014501 0.000e+00
## Animal Husbandry 18 2 0.0014485 1.662e-05
## Atmospheric Sciences 18 3 0.0014479 0.000e+00
## Biochemistry 1 2 0.0007515 6.836e-01
## Biodiversity & Conservation Biology 2 4 0.0014482 0.000e+00
## Bioinformatics 0 0 0.0007112 0.000e+00
## Biophysics 0 1 0.0007309 0.000e+00
## Biotechnology 25 2 0.0014497 0.000e+00
## Birds 4 2 0.0014475 0.000e+00
## Botany 6 2 0.0008215 1.428e-04
## Cell Biology 0 2 0.0007514 9.452e-01
## Developmental Biology & Embryology 0 0 0.0007112 0.000e+00
## Ecology 67 6 0.0014510 2.284e-04
## Environmental & Geological Engineering 0 1 0.0014498 0.000e+00
## Environmental Sciences 96 5 0.0014518 8.535e-04
## Evolutionary Biology 0 3 0.0014488 0.000e+00
## Food Science & Technology 20 2 0.0014490 8.402e-05
## Forests & Forestry 12 2 0.0014495 0.000e+00
## Geochemistry & Mineralogy 0 1 0.0014393 1.018e-05
## Geology 35 3 0.0014467 3.505e-04
## Hydrology 0 1 0.0014453 9.666e-05
## Insects & Arthropods 0 1 0.0008206 4.694e-04
## Marine Sciences Fisheries 60 3 0.0014512 0.000e+00
## Microbiology 21 2 0.0014492 0.000e+00
## Molecular Biology 0 2 0.0007513 1.000e+00
## Mycology 0 0 0.0007112 0.000e+00
## Oceanography 76 4 0.0014507 7.076e-04
## Paleontology 0 1 0.0014382 4.566e-05
## Pest Control & Pesticides 4 2 0.0008213 7.964e-04
## Plant Pathology 6 3 0.0008215 6.410e-04
## Proteomics & Peptides 0 1 0.0007309 0.000e+00
## Soil Sciences 0 1 0.0008207 7.466e-04
## Sustainable Development 0 0 0.0007112 0.000e+00
## Sustainable Energy 0 0 0.0007112 0.000e+00
## Virology 0 0 0.0007112 0.000e+00
## Wood Science & Technology 0 0 0.0007112 0.000e+00
## Zoology 0 4 0.0014488 0.000e+00
##
## $`2001`
## Class
## Agronomy Crop Science Agronomy Crop Science
## Animal Behavior Animal Behavior
## Animal Husbandry Animal Husbandry
## Atmospheric Sciences Atmospheric Sciences
## Biochemistry Biochemistry
## Biodiversity & Conservation Biology Biodiversity & Conservation Biology
## Bioinformatics Bioinformatics
## Biophysics Biophysics
## Biotechnology Biotechnology
## Birds Birds
## Botany Botany
## Cell Biology Cell Biology
## Developmental Biology & Embryology Developmental Biology & Embryology
## Ecology Ecology
## Environmental & Geological Engineering Environmental & Geological Engineering
## Environmental Sciences Environmental Sciences
## Evolutionary Biology Evolutionary Biology
## Food Science & Technology Food Science & Technology
## Forests & Forestry Forests & Forestry
## Geochemistry & Mineralogy Geochemistry & Mineralogy
## Geology Geology
## Hydrology Hydrology
## Insects & Arthropods Insects & Arthropods
## Marine Sciences Fisheries Marine Sciences Fisheries
## Microbiology Microbiology
## Molecular Biology Molecular Biology
## Mycology Mycology
## Oceanography Oceanography
## Paleontology Paleontology
## Pest Control & Pesticides Pest Control & Pesticides
## Plant Pathology Plant Pathology
## Proteomics & Peptides Proteomics & Peptides
## Soil Sciences Soil Sciences
## Sustainable Development Sustainable Development
## Sustainable Energy Sustainable Energy
## Virology Virology
## Wood Science & Technology Wood Science & Technology
## Zoology Zoology
## Between Degree Closeness Eigen
## Agronomy Crop Science 27 3 0.0021289 2.034e-03
## Animal Behavior 27 5 0.0021497 0.000e+00
## Animal Husbandry 19 2 0.0021439 1.008e-03
## Atmospheric Sciences 4 3 0.0021438 1.086e-03
## Biochemistry 0 2 0.0007734 7.085e-01
## Biodiversity & Conservation Biology 2 4 0.0021450 0.000e+00
## Bioinformatics 0 0 0.0007112 3.393e-04
## Biophysics 0 1 0.0007309 2.216e-04
## Biotechnology 36 2 0.0021514 8.160e-04
## Birds 22 3 0.0021504 1.955e-04
## Botany 17 2 0.0021263 5.168e-04
## Cell Biology 1 3 0.0007736 9.338e-01
## Developmental Biology & Embryology 1 2 0.0007736 2.032e-01
## Ecology 134 8 0.0021555 0.000e+00
## Environmental & Geological Engineering 0 1 0.0021513 2.784e-04
## Environmental Sciences 166 6 0.0021582 1.146e-03
## Evolutionary Biology 0 3 0.0021468 0.000e+00
## Food Science & Technology 22 2 0.0021449 8.486e-04
## Forests & Forestry 0 2 0.0021502 0.000e+00
## Geochemistry & Mineralogy 0 1 0.0021069 4.423e-05
## Geology 47 3 0.0021313 0.000e+00
## Hydrology 4 2 0.0021459 6.002e-04
## Insects & Arthropods 36 2 0.0021513 4.648e-04
## Marine Sciences Fisheries 94 3 0.0021559 0.000e+00
## Microbiology 26 2 0.0021462 7.396e-04
## Molecular Biology 0 3 0.0007736 1.000e+00
## Mycology 0 0 0.0007112 3.393e-04
## Oceanography 82 4 0.0021515 1.646e-04
## Paleontology 0 1 0.0021064 4.589e-05
## Pest Control & Pesticides 20 2 0.0021284 1.072e-03
## Plant Pathology 14 3 0.0021253 1.459e-03
## Proteomics & Peptides 0 1 0.0007309 2.216e-04
## Soil Sciences 59 3 0.0021540 1.662e-03
## Sustainable Development 0 0 0.0007112 3.393e-04
## Sustainable Energy 0 0 0.0007112 3.393e-04
## Virology 0 0 0.0007112 3.393e-04
## Wood Science & Technology 0 0 0.0007112 3.393e-04
## Zoology 0 4 0.0021460 0.000e+00
##
## $`2003`
## Class
## Agronomy Crop Science Agronomy Crop Science
## Animal Behavior Animal Behavior
## Animal Husbandry Animal Husbandry
## Atmospheric Sciences Atmospheric Sciences
## Biochemistry Biochemistry
## Biodiversity & Conservation Biology Biodiversity & Conservation Biology
## Bioinformatics Bioinformatics
## Biophysics Biophysics
## Biotechnology Biotechnology
## Birds Birds
## Botany Botany
## Cell Biology Cell Biology
## Developmental Biology & Embryology Developmental Biology & Embryology
## Ecology Ecology
## Environmental & Geological Engineering Environmental & Geological Engineering
## Environmental Sciences Environmental Sciences
## Evolutionary Biology Evolutionary Biology
## Food Science & Technology Food Science & Technology
## Forests & Forestry Forests & Forestry
## Geochemistry & Mineralogy Geochemistry & Mineralogy
## Geology Geology
## Hydrology Hydrology
## Insects & Arthropods Insects & Arthropods
## Marine Sciences Fisheries Marine Sciences Fisheries
## Microbiology Microbiology
## Molecular Biology Molecular Biology
## Mycology Mycology
## Oceanography Oceanography
## Paleontology Paleontology
## Pest Control & Pesticides Pest Control & Pesticides
## Plant Pathology Plant Pathology
## Proteomics & Peptides Proteomics & Peptides
## Soil Sciences Soil Sciences
## Sustainable Development Sustainable Development
## Sustainable Energy Sustainable Energy
## Virology Virology
## Wood Science & Technology Wood Science & Technology
## Zoology Zoology
## Between Degree Closeness Eigen
## Agronomy Crop Science 0 3 0.0025617 0.0008228
## Animal Behavior 55 5 0.0025814 0.0001545
## Animal Husbandry 36 2 0.0025744 0.0010058
## Atmospheric Sciences 4 3 0.0025619 0.0006393
## Biochemistry 6 3 0.0008214 0.7637118
## Biodiversity & Conservation Biology 93 5 0.0025839 0.0000000
## Bioinformatics 0 0 0.0007112 0.0001073
## Biophysics 0 1 0.0008212 0.0033143
## Biotechnology 33 2 0.0025730 0.0010267
## Birds 2 3 0.0025784 0.0001204
## Botany 104 3 0.0025773 0.0006245
## Cell Biology 6 3 0.0008214 0.9126029
## Developmental Biology & Embryology 4 2 0.0008213 0.1686625
## Ecology 49 7 0.0025831 0.0000000
## Environmental & Geological Engineering 0 1 0.0025727 0.0003717
## Environmental Sciences 139 6 0.0025830 0.0004583
## Evolutionary Biology 119 5 0.0025832 0.0000000
## Food Science & Technology 25 2 0.0025677 0.0011638
## Forests & Forestry 123 3 0.0025855 0.0000000
## Geochemistry & Mineralogy 0 1 0.0025041 0.0001895
## Geology 51 3 0.0025499 0.0001057
## Hydrology 15 2 0.0025681 0.0005428
## Insects & Arthropods 0 1 0.0024962 0.0003796
## Marine Sciences Fisheries 0 3 0.0025691 0.0000000
## Microbiology 37 3 0.0025672 0.0014992
## Molecular Biology 0 3 0.0008211 1.0000000
## Mycology 0 1 0.0025578 0.0004237
## Oceanography 79 4 0.0025729 0.0000000
## Paleontology 0 1 0.0025110 0.0002272
## Pest Control & Pesticides 26 2 0.0025444 0.0006727
## Plant Pathology 74 4 0.0025668 0.0009060
## Proteomics & Peptides 4 2 0.0008214 0.0401692
## Soil Sciences 136 4 0.0025847 0.0005743
## Sustainable Development 0 0 0.0007112 0.0001073
## Sustainable Energy 0 0 0.0007112 0.0001073
## Virology 0 1 0.0025569 0.0005894
## Wood Science & Technology 0 0 0.0007112 0.0001073
## Zoology 0 4 0.0025737 0.0000000
##
## $`2005`
## Class
## Agronomy Crop Science Agronomy Crop Science
## Animal Behavior Animal Behavior
## Animal Husbandry Animal Husbandry
## Atmospheric Sciences Atmospheric Sciences
## Biochemistry Biochemistry
## Biodiversity & Conservation Biology Biodiversity & Conservation Biology
## Bioinformatics Bioinformatics
## Biophysics Biophysics
## Biotechnology Biotechnology
## Birds Birds
## Botany Botany
## Cell Biology Cell Biology
## Developmental Biology & Embryology Developmental Biology & Embryology
## Ecology Ecology
## Environmental & Geological Engineering Environmental & Geological Engineering
## Environmental Sciences Environmental Sciences
## Evolutionary Biology Evolutionary Biology
## Food Science & Technology Food Science & Technology
## Forests & Forestry Forests & Forestry
## Geochemistry & Mineralogy Geochemistry & Mineralogy
## Geology Geology
## Hydrology Hydrology
## Insects & Arthropods Insects & Arthropods
## Marine Sciences Fisheries Marine Sciences Fisheries
## Microbiology Microbiology
## Molecular Biology Molecular Biology
## Mycology Mycology
## Oceanography Oceanography
## Paleontology Paleontology
## Pest Control & Pesticides Pest Control & Pesticides
## Plant Pathology Plant Pathology
## Proteomics & Peptides Proteomics & Peptides
## Soil Sciences Soil Sciences
## Sustainable Development Sustainable Development
## Sustainable Energy Sustainable Energy
## Virology Virology
## Wood Science & Technology Wood Science & Technology
## Zoology Zoology
## Between Degree Closeness Eigen
## Agronomy Crop Science 40 3 0.0025272 1.089e-03
## Animal Behavior 49 5 0.0025643 0.000e+00
## Animal Husbandry 31 2 0.0025551 3.452e-04
## Atmospheric Sciences 4 3 0.0025545 7.333e-04
## Biochemistry 0 2 0.0007733 7.519e-01
## Biodiversity & Conservation Biology 12 5 0.0025594 0.000e+00
## Bioinformatics 0 0 0.0007112 1.345e-04
## Biophysics 0 1 0.0007310 1.069e-05
## Biotechnology 40 2 0.0025631 7.572e-04
## Birds 0 3 0.0025618 0.000e+00
## Botany 29 2 0.0025194 2.195e-04
## Cell Biology 2 3 0.0007737 9.066e-01
## Developmental Biology & Embryology 2 2 0.0007737 1.779e-01
## Ecology 112 7 0.0025702 0.000e+00
## Environmental & Geological Engineering 0 1 0.0025627 2.207e-04
## Environmental Sciences 200 7 0.0025761 1.111e-03
## Evolutionary Biology 5 4 0.0025591 0.000e+00
## Food Science & Technology 23 2 0.0025551 3.529e-04
## Forests & Forestry 14 2 0.0025622 0.000e+00
## Geochemistry & Mineralogy 0 1 0.0025117 3.229e-04
## Geology 51 3 0.0025527 4.954e-04
## Hydrology 5 2 0.0025560 3.544e-04
## Insects & Arthropods 30 2 0.0025558 3.691e-04
## Marine Sciences Fisheries 103 3 0.0025709 0.000e+00
## Microbiology 42 3 0.0025570 5.703e-04
## Molecular Biology 0 3 0.0007736 1.000e+00
## Mycology 0 0 0.0007112 1.345e-04
## Oceanography 89 4 0.0025676 7.220e-04
## Paleontology 0 1 0.0025064 3.744e-04
## Pest Control & Pesticides 21 2 0.0025150 4.695e-04
## Plant Pathology 24 3 0.0025166 7.327e-04
## Proteomics & Peptides 0 1 0.0007310 1.068e-05
## Soil Sciences 75 3 0.0025701 9.237e-04
## Sustainable Development 0 1 0.0025640 1.921e-04
## Sustainable Energy 0 0 0.0007112 1.345e-04
## Virology 0 1 0.0025468 1.221e-04
## Wood Science & Technology 0 0 0.0007112 1.345e-04
## Zoology 48 5 0.0025633 0.000e+00yearstats<-melt(yearstats)
ggplot(yearstats,aes(x=L1,y=value,col=Class)) + geom_point() +geom_line(aes(group=Class)) + facet_wrap(~variable,scales="free",ncol=1)
Connectance through time
yeardat<-lapply(yearcompare,function(x){
siteXspp<-droplevels(as.data.frame.array(table(x$Author,x$Class)))
#drop empty rows and colums
siteXspp<-siteXspp[rownames(siteXspp) %in% names(which(apply(siteXspp,1,sum) > 0)),colnames(siteXspp) %in% names(which(apply(siteXspp,2,sum) > 0))]
#Compare disciplines
topics<-1-as.matrix(vegdist(t(siteXspp),"horn"))
diag(topics)<-NA
topics[upper.tri(topics)]<-NA
return(topics)
})
yeardat<-melt(yeardat)
colnames(yeardat)<-c("To","From","Niche.Overlap","Year")Remove extremely weak connections
#remove very weak connections
#work from an example data
#make into characters
yeardat$To<-as.character(yeardat$To)
yeardat$From<-as.character(yeardat$From)
#remove weak connections
exdat<-group_by(yeardat,To,From) %>% filter(Niche.Overlap>0.05 & !is.na(Niche.Overlap))
exdat$Combo<-paste(exdat$To,exdat$From,sep="-")
#plot
ggplot(exdat,aes(x=Year,y=Niche.Overlap,col=From)) + geom_point() + geom_line(aes(group=Combo)) + facet_wrap(~To,scales="free",ncol=3) + theme_bw() + geom_text(data=exdat[exdat$Year==m[length(m)/2],],aes(label=From),size=4) 
ggsave("Figures/LinkTime.svg",dpi=300)
ggsave("Figures/LinkTime.jpeg",height=10,width=14,dpi=300)trend estimation
Its not clear to me if i need to use a time-series model. The connection at time A should be independent of connection at time A+1. While they may be related due to the trend - there is no mechanistic connection among publications between years. Its not like a population, where the number of available producers directly influences the offspring in the next year. For the moment, i’m just using a linear model with year as a continious variable. This probably needs to change.
first pass just fit a linear line and determine if its positive or negative
exdat$Combo<-paste(exdat$To,exdat$From,sep="-")
#year is a number value for the moment
exdat$Year<-as.numeric(exdat$Year)-1995
sdat<-split(exdat,exdat$Combo)
#get rid of combinations with less than ten years of points
sdat<-sdat[lapply(sdat,nrow) > 2]
#
# Break up d by state, then fit the specified model to each piece and
# return a list
tmod<-rbind_all(lapply(sdat,function(df){
tdat<-tidy(lm(Niche.Overlap ~ Year, data = df))
tdat<-tdat[tdat$term =="Year",]
tdat$Combo<-unique(df$Combo)
return(tdat)
}))
#extract names into columns
tmod$To<-str_match(tmod$Combo,"(.*)-")[,2]
tmod$From<-str_match(tmod$Combo,"-(.*)")[,2]Visualize effect over time
Positive values are significantly increasing connections Negative values are significantly decreasing connections
tmod$svalue<-scale(tmod$estimate)
ggplot(tmod[tmod$p.value < 0.05 & tmod$term=="Year",],aes(x=To,y=From,fill=estimate)) + geom_tile() + theme_bw() + scale_fill_gradientn(colours=c("blue","gray","red"),limits=c(-max(tmod$estimate),max(tmod$estimate))) + theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) + labs(x="",y="")
ggsave("InteractionsTime.svg",dpi=300)
ggsave("InteractionsTime.jpeg",height=7,width=7) D3 Networks
D3 Visualizations
The wonderful D3 package connections!
MisLinks<-melt(topics)
#remove very weak connections
MisLinks<-MisLinks[MisLinks$value > 0.05,]
MisLinks$value<-MisLinks$value*10
colnames(MisLinks)<-c("To","From","value")
MisLinks$To<-as.character(MisLinks$To)
MisLinks$From<-as.character(MisLinks$From)
MisNodes<-data.frame(name=as.factor(sort(as.character(unique(c(MisLinks$To,MisLinks$From))))))
#Add groups
MisNodes$group<-as.integer(1)
MisLinks$source<-as.integer(sapply(MisLinks$To,function(x) which(x ==MisNodes$name)))-1
MisLinks$target<-as.integer(sapply(MisLinks$From,function(x) which(x ==MisNodes$name)))-1
#Order by source
MisLinks<-MisLinks[order(MisLinks$source),]
simpleNetwork(MisLinks,fontSize = 15)simpleNetwork(MisLinks,height=500,width=700) %>% saveNetwork(file = 'Net1.html',selfcontained=F)Force based network
d3Network::d3ForceNetwork(Links = MisLinks, Nodes = MisNodes, Source = "source",Target = "target", Value = "value", NodeID = "name", Group = "group", opacity = 0.9,file="Net3.html") save.image("Analysis.RData")